Mercurial > repos > ufz > iphop_predict

comparison iphop.xml @ 2:be0d13020aec draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/Helmholtz-UFZ/ufz-galaxy-tools/blob/main/tools/iphop/ commit e93300e2db7217d84659e199d3f23e280de80ccb
author ufz
date Wed, 11 Feb 2026 14:31:52 +0000
parents d357350b6da0
children
comparison
equal deleted inserted replaced
1:d357350b6da0 2:be0d13020aec
1 <tool id="iphop_predict" name="iPHoP predict" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="23.0" license="MIT"> 1 <tool id="iphop_predict" name="iPHoP predict" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="23.0" license="MIT">
2 <description>host of input bacteriophage/archaeal virus genomes</description> 2 <description>host of input bacteriophage/archaeal virus genomes</description>
3 <macros> 3 <macros>
4 <token name="@TOOL_VERSION@">1.3.3</token> 4 <token name="@TOOL_VERSION@">1.4.2</token>
5 <token name="@VERSION_SUFFIX@">0</token> 5 <token name="@VERSION_SUFFIX@">0</token>
6 </macros> 6 </macros>
7 <xrefs> 7 <xrefs>
8 <xref type="bio.tools">iphop</xref> 8 <xref type="bio.tools">iphop</xref>
9 </xrefs> 9 </xrefs>
23 ]]></command> 23 ]]></command>
24 <inputs> 24 <inputs>
25 <param argument="--fa_file" type="data" format="fasta" label="FASTA formatted virus sequences"/> 25 <param argument="--fa_file" type="data" format="fasta" label="FASTA formatted virus sequences"/>
26 <param argument="--db_dir" type="select" label="Reference database"> 26 <param argument="--db_dir" type="select" label="Reference database">
27 <options from_data_table="iphop"> 27 <options from_data_table="iphop">
28 <filter type="regexp" column="version" value="^(iPHoP_db_Jun25_rw|test_version)$"/>
28 <validator type="no_options" message="No reference data available. Contact your Galaxy admin."/> 29 <validator type="no_options" message="No reference data available. Contact your Galaxy admin."/>
29 </options> 30 </options>
30 </param> 31 </param>
31 <param argument="--min_score" type="integer" value="90" min="75" max="100" label="Minimum confidence score" help="Minimum confidence score for final output. Default of 90 corresponds to ~10% FDR (roughly). For ~5% overall (roughly) estimated FDR, use a minimum score of 95, etc."/> 32 <param argument="--min_score" type="integer" value="90" min="75" max="100" label="Minimum confidence score" help="Minimum confidence score for final output. Default of 90 corresponds to ~10% FDR (roughly). For ~5% overall (roughly) estimated FDR, use a minimum score of 95, etc."/>
32 <param argument="--no_qc" type="boolean" truevalue="--no_qc" falsevalue="" label="Bypass the automated QC" help="Bypass the automated QC that filters out input sequences with > 10% Ns or with characters other than ATCGN. Warning: if set to true, low-quality sequences (with Ns or unusual characters) may lead to unexpected failures at multiple steps. (default = False)"/> 33 <param argument="--no_qc" type="boolean" truevalue="--no_qc" falsevalue="" label="Bypass the automated QC" help="Bypass the automated QC that filters out input sequences with > 10% Ns or with characters other than ATCGN. Warning: if set to true, low-quality sequences (with Ns or unusual characters) may lead to unexpected failures at multiple steps. (default = False)"/>
40 <!-- <test> 41 <!-- <test>
41 <param name="fa_file" value="test_input_phages.fna" ftype="fasta"/> 42 <param name="fa_file" value="test_input_phages.fna" ftype="fasta"/>
42 <param name="db_dir" value="db2"/> 43 <param name="db_dir" value="db2"/>
43 <output name="detailed_per_tool"> 44 <output name="detailed_per_tool">
44 <assert_contents> 45 <assert_contents>
45 <has_n_lines n="190"/> 46 <has_n_lines n="192"/>
46 <has_n_columns n="10" sep="," comment="#"/> 47 <has_n_columns n="10" sep="," comment="#"/>
47 </assert_contents> 48 </assert_contents>
48 </output> 49 </output>
49 <output name="host_genome"> 50 <output name="host_genome">
50 <assert_contents> 51 <assert_contents>
51 <has_line line="Virus,Host genome,Host taxonomy,Main method,Confidence score,Additional methods"/> 52 <has_line line="Virus,Host genome,Host taxonomy,Main method,Confidence score,Additional methods"/>
52 <has_n_lines n="119"/> 53 <has_n_lines n="27"/>
53 <has_n_columns n="6" sep=","/> 54 <has_n_columns n="6" sep=","/>
54 </assert_contents> 55 </assert_contents>
55 </output> 56 </output>
56 <output name="host_genus"> 57 <output name="host_genus">
57 <assert_contents> 58 <assert_contents>
58 <has_line line="Virus,AAI to closest RaFAH reference,Host genus,Confidence score,List of methods"/> 59 <has_line line="Virus,AAI to closest RaFAH reference,Host genus,Confidence score,List of methods"/>
59 <has_n_lines n="6"/> 60 <has_n_lines n="8"/>
60 <has_n_columns n="5" sep=","/> 61 <has_n_columns n="5" sep=","/>
61 </assert_contents> 62 </assert_contents>
62 </output> 63 </output>
63 </test> --> 64 </test> -->
64 </tests> 65 </tests>
85 - the level of amino-acid similarity (AAI) between the query and the genomes in the RaFAH phage database, 86 - the level of amino-acid similarity (AAI) between the query and the genomes in the RaFAH phage database,
86 - the predicted host genus, 87 - the predicted host genus,
87 - the confidence score calculated from all tools, and 88 - the confidence score calculated from all tools, and
88 - the list of scores for individual classifiers obtained for this virus-host pair. 89 - the list of scores for individual classifiers obtained for this virus-host pair.
89 90
90 - for the detailed score by classifier, "RaFAH" represents the score derived from RaFAH (https://pubmed.ncbi.nlm.nih.gov/34286299/), iPHoP-RF is the score derived from all host-based tools, CRISPR the score derived only from CRISPR hits, and blast the score derived only from blastn hits 91 - for the detailed score by classifier, "RaFAH" represents the score derived from RaFAH (https://doi.org/10.1016/j.patter.2021.100274), iPHoP-RF is the score derived from all host-based tools, CRISPR the score derived only from CRISPR hits, and blast the score derived only from blastn hits
91 - all virus-host pairs for which the confidence score is higher than the selected score cutoff (default = 90) are included, so each virus may be associated with multiple predictions 92 - all virus-host pairs for which the confidence score is higher than the selected score cutoff (default = 90) are included, so each virus may be associated with multiple predictions
92 - when multiple predictions are available for a query virus, typical standard practices is to use the one with the highest score 93 - when multiple predictions are available for a query virus, typical standard practices is to use the one with the highest score
93 94
94 Host prediction to genome 95 Host prediction to genome
95 96